Portfolio / 2026J. Bailey

Jack
Bailey

Founder & CEO of Discera.

Routing writing

I build an AI router that sends each message to the model best suited for it. Scroll, and watch it work:

Discera router · routing illustrationFig. 01

>

WritingCodeImages

scroll to route ↓

The motto

Every task has a different winner.

What my research company, Noesira, is built on.

Inside an AI · illustrated tour

01 / 07

Noesira field trip · illustrated tour

Inside
an AI

An illustrated journey from computing hardware to a model’s reply, in six stops. Keep scrolling.

130 FT AI DATA CENTER · ILLUSTRATION

Ask one of the big AI services a question, and the work starts in a building like this: a data center packed with computers running day and night.

Fig. 03·1 — data center

GPU NODE 07 7 UNITS .

Inside: rack after rack of GPUs — chips built to do the same kind of math over and over, at enormous scale.

Fig. 03·2 — GPU rack

ONE GPU · COMPUTE DIE · ILLUSTRATION

One GPU spreads the work across thousands of small cores, all computing at the same time.

Fig. 03·3 — one GPU

PROMPT NEURAL NETWORK · ILLUSTRATION

Together they run a model: a vast web of connections, each one adjusted during training on enormous amounts of data.

Fig. 03·4 — the model

0.31-1.070.882.40-0.151.560.73ONE WEIGHT-0.920.041.19-0.442.010.37-1.630.900.12-0.581.840.66-2.20 MODEL WEIGHTS · ILLUSTRATION

Each connection carries a number the model learned — a weight. Your prompt is turned into tokens and processed through billions of them.

Fig. 03·5 — weights

MODEL OUTPUT · ILLUSTRATION

Out comes the reply, one token at a time. Noesira’s question: which model does it best?

Fig. 03·6 — the answer

01About short version

02Work what I run

03Discera the AI that chooses for you

I built Discera because no single model is best at everything. It's one prompt box that reads your task and sends it to the model that handles it best.

? WRITING CODE IMAGES

One prompt in, the right model out

Fig. 02

Discera reports 94.1% average routing accuracy across three 147-question test sets, versus 73.7% for the original router it was measured against on the same benchmark. As published on discera.chat

Visit Disceradiscera.chat (access is limited by code)↗

04Noesira independent AI research

I started Noesira to rank AI models by what they're actually best at: writing, coding, reasoning, research, routing. It's compiled from public benchmarks and arenas, and published with the sources attached.

Visit Noesiranoesira.org↗